Abstract This paper describes the development of a model based on artificial neural networks (ANN) which aims to predict the concentration of nitrates in river water. Another 26 water quality parameters were also monitored and used as input parameters. The models were trained and tested with data from ten monitoring stations on the Danube River, located in its course through Serbia, for the period from 2011 to 2016. Multi-layer perceptron, standard three-layer network is used to develop models and two input variable selection techniques are used to reduce the number of input variables. The obtained results have shown the ability of ANN to predict the nitrate concentration in both developed models with a value of mean absolute error of 0.53 and 0.42 mg/L for the test data. Also, the application of IVS has contributed to reduce the number of input variables and to increase the performance of the model, especially in the case of variance inflation factor (VIF) analysis where the estimation of multicollinearity among variables and the elimination of excessive variables significantly influenced the prediction abilities of the ANN model, r – 0.91.

This study focuses on the issues related to the waste management in river ports in general and, particularly, in ports on the river Danube's flow through Serbia. The ports of Apatin, Bezdan, Backa Palanka, Novi Sad, Belgrade, Smederevo, Veliko Gradiste, Prahovo and Kladovo were analyzed. The input data (number of watercrafts, passengers and crew members) were obtained from harbor authorities for the period 2005-2009. The quantities of solid waste generated on both cruise and cargo ships are considered in this article. As there is no strategy for waste treatment in the ports in Serbia, these data are extremely valuable for further design of equipment for waste treatment and collection. Trends in data were analyzed and regression models were used to predict the waste quantities in each port in next 3 years. The obtained trends could be utilized as the basis for the calculation of the equipment capacities for waste selection, collection, storage and treatment. The results presented in this study establish the need for an organized management system for this type of waste, as well as suggest where the terminals for collection, storage and treatment of solid waste from ships should be located.

This paper provides insight into the quality of groundwater used for public water supply on the territory of Temerin municipality (Vojvodina, Serbia). The following parameters were measured: color, turbidity, pH, KMnO4 consumption, total dissolved solids (TDS), EC, NH4+, Cl-, NO2-, NO3-, Fe, Mn, As, Ca2+, Mg2+, SO4(2-), HCO3-, K+, and Na+. The correlations and ratios among parameters that define the chemical composition were determined aiming to identify main processes that control the formation of the chemical composition of the analyzed waters. Groundwater from three analyzed sources is Na-HCO3 type. Elevated organic matter content, ammonium ion content, and arsene content are characteristic for these waters. The importance of organic matter decay is assumed by positive correlation between organic matter content and TDS, and HCO3- content. There is no evidence that groundwater chemistry is determined by the depth of captured aquifer interval. The main natural processes that control the chemistry of all analyzed water are cation exchange and feldspar weathering. The dominant cause of As concentration in groundwater is the use of mineral fertilizers and of KMnO4 in urban area. The concentration of As and KMnO4 in the observed sources is inversely proportional to the distance from agricultural land and urban area. 2D model of distribution of As and KMnO4 is done, and it is applicable in detecting sources of pollution. By using this model, we can quantify the impact of certain pollutants on unfavorable content of some parameters in groundwater.

No abstract

No abstract